Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepSeek-V4-Flash Update

api-docs.deepseek.com

Post reply on HN
Print view View original

291–300 of 362 posts

Re: DeepSeek-V4-Flash Update

#291

Post by anigbrowl »

maweaver wrote: post #269
lionkor wrote: post #50

I use deepseek for a lot of my personal day-to-day agent needs, and I will simply put this here and let this speak for itself, last 30 days: - Cost: $4.55USD - API requests: 3,467 - Tokens: 323,183,886 And as an engineer who leads a small team, I have very high standards for quality, and these carry across to my personal projects where I use deepseek. It has not disappointed at all for coding or review tasks. For eve…

You are using DeepSeek's services directly? Doesn't that end up sending at least snippets/chunks of code to a server where it is subject to Chinese government data access laws? Even if I was okay with that, my organization would never be. And even if they were, our partners/vendors/customers would not be. I think that's the sticking point for a lot of people.

So go with some other provider who hosts the models like OpenRouter if are worried about this.

Re: DeepSeek-V4-Flash Update

#293

Post by dghlsakjg »

u8080 wrote: post #274
dghlsakjg wrote: post #248

Earlier quoted context omitted.

Openrouter has cheaper inference than deepseek for the prior version of v4 flash, which I suspect will happen within a day or two with this version, and they don’t offer subscriptions. Are you confusing it with opencode?

No, maybe I've checked too much time ago, but direct DS was cheaper for all versions - also I had issues with openrouter providers availability

There are numerous providers offering full weight versions for a significant discount.

Availability and rate limiting can be an issue, though. I’ve found that constraining the providers works well to solve that though.

Re: DeepSeek-V4-Flash Update

#294

Post by lionkor »

rzerowan wrote: post #276
lionkor wrote: post #169

Earlier quoted context omitted.

Yes, gladly! I have not yet open-sourced my skills etc., but I can give some insight and share a couple here. Review is a skill, as in, a SKILL.md with a folder full of references: - SKILL.md: https://gist.github.com/lionkor/161525be858d1d75db4c13c0f093... - references/output-contract.md: https://gist.github.com/lionkor/8c68e33becef7a21f8408c7dc119... - references/review-lenses.md: https://gist.github.com/lionkor/0a8…

Which languages are the reviews most successful on in your work so far? Im assumining js/python , would a similar output be feasible on lower level c++ or C#/Java.

No js or python, it's mostly C#, Rust, and C++. They're helpful/useful on all of those, I've also used the review skill on shell scripts, GitLab pipelines, Powershell scripts, C, and a couple other odd things. It's almost never useless to run it on something, it usually finds things, even if they're sometimes not very major.

Re: DeepSeek-V4-Flash Update

#295

Post by lionkor »

brcmthrowaway wrote: post #268
lionkor wrote: post #50

I use deepseek for a lot of my personal day-to-day agent needs, and I will simply put this here and let this speak for itself, last 30 days: - Cost: $4.55USD - API requests: 3,467 - Tokens: 323,183,886 And as an engineer who leads a small team, I have very high standards for quality, and these carry across to my personal projects where I use deepseek. It has not disappointed at all for coding or review tasks. For eve…

OpenRouter?

No, platform.deepseek.com for me! The caching is super important, not sure how open router performs, I haven't tried it.

Re: DeepSeek-V4-Flash Update

#296

Post by lionkor »

maweaver wrote: post #269
lionkor wrote: post #50

I use deepseek for a lot of my personal day-to-day agent needs, and I will simply put this here and let this speak for itself, last 30 days: - Cost: $4.55USD - API requests: 3,467 - Tokens: 323,183,886 And as an engineer who leads a small team, I have very high standards for quality, and these carry across to my personal projects where I use deepseek. It has not disappointed at all for coding or review tasks. For eve…

You are using DeepSeek's services directly? Doesn't that end up sending at least snippets/chunks of code to a server where it is subject to Chinese government data access laws? Even if I was okay with that, my organization would never be. And even if they were, our partners/vendors/customers would not be. I think that's the sticking point for a lot of people.

Yes all of it goes straight to China! All of it is also open source or source available, or will be in the future. The stuff that isn't is trivial enough.

For any work with protected intellectual property, I use other providers, for the contractual guarantees, but I think it would be silly to think that OpenAI or Anthropic are not training on literally all data they get. How could you ever tell if they did? They can just claim the data was mislabelled, or ignore the accusations. If you have serious IP, use only local models.

Re: DeepSeek-V4-Flash Update

#297

Post by applicative »

satvikpendem wrote: post #245
applicative wrote: post #184

Earlier quoted context omitted.

Xi going to shut down open-weighting of them in a matter of months. No one seriously doubts this. They will be too powerful and they will be gone.

He explicitly said he wants open weight models at his recent speech at an AI conference in Shanghai: https://news.ycombinator.com/item?id=48970449#48970784

The Chinese equivalent of the expression 'open weights' appears nowhere in this talk. You believed the Western press. Chinese AIs are not typically open. The most important by far is Bytedance.

Re: DeepSeek-V4-Flash Update

#298

Post by applicative »

ricardobeat wrote: post #244
applicative wrote: post #228

Earlier quoted context omitted.

> Maybe once Chinese models have speed, cost, and intelligence beat but right now they don't. Yes this is why I referred to 'months' and was downvoted by people who can't distinguish their politics from reality. You are restating exactly the text you are criticizing. This is the nature of mechanical parrotlike repetition of propaganda: a) You can have 'frontier' models with closed weights. Your sentence is basically…

The latest ByteDance Seed model is behind Opus 4.6 in performance. It’s not even in the conversation atm. The parent made a totally coherent commment that China closing off their open weight models would cede the frontier (and majority of AI users worldwide) to the USA. Nothing you said counters that point.

Bytedance models completely pervade business use across China. It is the OpenAI of China, whether you think its a good model or not.
Post reply on HN